# Low-Resource Self-Supervised Learning with SSL-Enhanced TTS

arXiv: https://arxiv.org/abs/2309.17020 · HTML: https://mlsanity.com/paper/2309.17020/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2023.

## Built on by (most cited first, 4 of 4)

- [Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility](https://mlsanity.com/paper/2409.09357/) (2024)
- [SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models](https://mlsanity.com/paper/2509.14270/) (2025)
- [Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation](https://mlsanity.com/paper/2409.11003/) (2024)
- [Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations](https://mlsanity.com/paper/2505.05056/) (2025)

## Abstract (arXiv)

Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper proposes to address this challenge by leveraging synthetic speech to augment a low-resource pre-training corpus. We construct a high-quality text-to-speech (TTS) system with limited resources using SSL features and generate a large synthetic corpus for pre-training. Experimental results demonstrate that our proposed approach effectively reduces the demand for speech data by 90% with only slight performance degradation. To the best of our knowledge, this is the first work aiming to enhance low-resource self-supervised learning in speech processing.